Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add georgekhananaev/claude-skills-vault --skill mongodb-atlas-cligit clone --depth 1 https://github.com/georgekhananaev/claude-skills-vaultWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/georgekhananaev/claude-skills-vault/mongodb-atlas-cli)<a href="https://agentmods.dev/skills/georgekhananaev/claude-skills-vault/mongodb-atlas-cli"><img src="https://agentmods.dev/badge/skills/georgekhananaev/claude-skills-vault/mongodb-atlas-cli/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/georgekhananaev/claude-skills-vault/mongodb-atlas-cli"><img src="https://agentmods.dev/badge/skills/georgekhananaev/claude-skills-vault/mongodb-atlas-cli.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium MCP Rug Pull · line 63 Docker image references without a specific tag (:latest is implicit) or digest (@sha256:...) can be silently replaced by a malicious image.Fix: Pin the image: image:tag or image@sha256:abc123
- medium MCP Rug Pull · line 64 Docker image references without a specific tag (:latest is implicit) or digest (@sha256:...) can be silently replaced by a malicious image.Fix: Pin the image: image:tag or image@sha256:abc123
- low Tool Misuse · line 64 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00135 | $0.03645 |
| Opus 5 | $0.00068 | $0.01822 |
| Sonnet 5 | $0.00027 | $0.00729 |
| Haiku 4.5 | $0.00014 | $0.00364 |
Grade A, and why
mongodb-atlas-cli scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 358 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MongoDB Atlas CLI Skill
Comprehensive coverage of MongoDB Atlas operations w/ strict safety guarantees. Optimized for the loop: read Performance Advisor → review suggestions → create the right indexes safely. Never destructive.
When to Use
Invoke when the user wants to:
- Connect to Atlas, list clusters/processes/projects
- Pull Performance Advisor output (slow queries, suggested indexes, schema advice, drop hints)
- Read cluster/process/database metrics, alerts, backup status
- List existing indexes w/ live access counts (mongosh-based)
- Explain a query (find or aggregate)
- Create indexes — single, compound, TTL, sparse, partial, unique, geospatial, hashed, Atlas Search, Vector Search
- Diff two audits week-over-week
- Audit overall cluster performance
- Diagnose slow queries before code changes
Do NOT use for any destructive op. Direct CRUD against data is also out of scope (use mongosh directly or the official MongoDB MCP server — see Integration).
Hard Safety Boundaries
| Category | Op | Action |
|---|---|---|
| Read | clusters/processes/metrics/logs/projects | Allowed, no confirm |
| Read | performanceAdvisor (all subcmds) | Allowed, no confirm |
| Read | api performanceAdvisor list* | Allowed, no confirm |
| Read | alerts/events/backups list, dbusers list | Allowed, no confirm |
| Read | clusters search indexes list | Allowed, no confirm |
| Read | mongosh: getIndexes, $indexStats, .explain(), getProfilingStatus | Allowed, no confirm |
| Write (additive) | clusters indexes create |
Requires --confirm + dry-run + duplicate pre-flight |
| Write (additive) | clusters search indexes create |
Requires --confirm + dry-run |
| Destructive | delete, drop, terminate, pause, restore, kill, force |
REFUSE — never run, even w/ user request |
| Destructive | dbusers create/update/delete |
REFUSE — auth changes can lock prod |
| Destructive | networking * writes, accessLists delete |
REFUSE — can sever connectivity |
| Destructive | backups restore / snapshot delete |
REFUSE — overwrites data |
| Destructive | clusters indexes delete |
REFUSE — even if advisor suggests dropping; only INFORM the user |
What ships with it
31 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/atlas-search.md 4.3 KB
- references/cli-commands.md 4.2 KB
- references/index-strategy.md 3.8 KB
- references/index-types.md 8.8 KB
- references/local-vs-atlas.md 6.2 KB
- references/mongosh-integration.md 4.4 KB
- references/performance-advisor.md 4.6 KB
- references/quick-recipes.md 6.6 KB
- references/safety-boundaries.md 4.0 KB
- references/troubleshooting.md 3.6 KB
- scripts/_common.py 11 KB runs code
- scripts/_mongo.py 6.5 KB runs code
- scripts/alerts.py 2.6 KB runs code
- scripts/atlas_search_create.py 5.5 KB runs code
- scripts/atlas_search_list.py 3.7 KB runs code
- scripts/audit_diff.py 7.2 KB runs code
- scripts/backup_status.py 4.5 KB runs code
- scripts/cluster_health.py 4.7 KB runs code
- scripts/drop_index_hints.py 4.3 KB runs code
- scripts/events.py 2.9 KB runs code
- scripts/explain_query.py 6.9 KB runs code
- scripts/index_build_status.py 4.1 KB runs code
- scripts/list_indexes.py 6.0 KB runs code
- scripts/namespaces.py 3.0 KB runs code
- scripts/performance_audit.py 5.1 KB runs code
- scripts/profiler_status.py 3.5 KB runs code
- scripts/safe_index_create.py 17 KB runs code
- scripts/schema_advice.py 3.8 KB runs code
- scripts/slow_queries.py 4.1 KB runs code
- scripts/suggest_indexes.py 4.6 KB runs code
- scripts/validate_env.py 6.3 KB runs code
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 8d ago First seen · 358 lines · 135 tokens per session scan A e6ac42f0034c
mongodb-atlas-cli is a skill published in the GitHub repository georgekhananaev/claude-skills-vault (28 stars, last pushed 1mo ago), licensed MIT. It adds 135 tokens to every session and 3,645 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
316-frameworks-spring-mongodb-migrations-mongock
Use when you need to add or review Mongock MongoDB data migrations in a Spring Boot application — including Maven coordinates, Spring Data MongoDB drivers, migration scan packages, @ChangeUnit classes, lock/transaction settings, and optional policy-approved MongoDB integration verification. This should trigger for…
416-frameworks-quarkus-mongodb-migrations-mongock
Use when you need to add or review Mongock MongoDB data migrations in a Quarkus application — including the Quarkiverse Mongock extension, Quarkus MongoDB client configuration, migrate-at-start, @ChangeUnit classes, lock/transaction settings, and Quarkus test verification. This should trigger for requests such as Add…
516-frameworks-micronaut-mongodb-migrations-mongock
Use when you need to add or review Mongock MongoDB data migrations in a Micronaut application — including Mongock runner/driver selection, Micronaut bean wiring, migration scan packages, @ChangeUnit classes, lock/transaction settings, and Testcontainers verification. This should trigger for requests such as Add…
705-technologies-nosql-mongodb
Use when you need framework-agnostic MongoDB and non-relational database query guidance — document schema design, collection modeling, JSON Schema validation, indexes, aggregation pipelines, query performance, consistency trade-offs, transactions, and operational safety — without choosing Spring Boot, Quarkus, or…
315-frameworks-spring-mongodb
Use when you need to design or implement MongoDB data access in Spring Boot — including document modeling, Spring Data Mongo repositories/templates, indexing, optimistic concurrency, and error handling. This should trigger for requests such as Add MongoDB in Spring Boot; Review Spring Data Mongo design; Improve error…
415-frameworks-quarkus-mongodb
Use when you need MongoDB persistence in Quarkus — including Panache Mongo entities/repositories, document design, indexes, transactions where applicable, and error handling. This should trigger for requests such as Add MongoDB in Quarkus; Review Quarkus Mongo Panache design; Improve Mongo error handling in Quarkus…